Decoding Protein Aggregation through Computational Approach: Identification and Scoring of Aggregation-Prone Regions in Protein Sequences

Protein aggregation is a critical phenomenon associated with numerous neurodegenerative and systemic diseases. Understanding the propensity of proteins to aggregate is essential for unraveling the molecular basis of these disorders and for design and engineering of novel proteins or modulating the activity/stability of enzymatic proteins. Here, we present APR-Score, a novel machine-learning based computational method designed to identify aggregation-prone regions within protein sequences. ARP-Score leverages a combination of sequence-based features to predict regions of proteins that are prone to aggregate. The APR-Score harnessed the information ingrained in the compiled sequence and structural features to provide state-of-the-art accuracy. The APR-Score is assessed by conducting rigorous cross-validation experiments on the training dataset and further validated on an independent test dataset. The APR-Score prediction models demonstrated robustness and reliability in discriminating aggregation-prone regions from non-aggregating ones on an independent dataset, achieving Mathews correlation coefficient (MCC) 0.81, precision 0.89, and F1-Score 0.91. The APR-Score offers a valuable tool for researchers investigating protein aggregation-related diseases, as it can expedite the identification of aggregation-prone regions, aiding in the development of targeted therapies and diagnostic tools. The computational protein design and engineering regimes can be facilitated through APR-Score based identification and screening of aggregation prone protein sequences.